Experimenting with Transitive Verbs in a DisCoCat

Abstract

Formal and distributional semantic models offer complementary benefits in modeling meaning. The categorical compositional distributional (DisCoCat) model of meaning of Coecke et al. (arXiv:1003.4394v1 [cs.CL]) combines aspected of both to provide a general framework in which meanings of words, obtained distributionally, are composed using methods from the logical setting to form sentence meaning. Concrete consequences of this general abstract setting and applications to empirical data are under active study (Grefenstette et al., arxiv:1101.0309; Grefenstette and Sadrzadeh, arXiv:1106.4058v1 [cs.CL]). . In this paper, we extend this study by examining transitive verbs, represented as matrices in a DisCoCat. We discuss three ways of constructing such matrices, and evaluate each method in a disambiguation task developed by Grefenstette and Sadrzadeh (arXiv:1106.4058v1 [cs.CL]).

5 pages, to be presented at GEMS 2011, as part of EMNLP'11 workshops

References in corpus (1)

• Experimental Support for a Categorical Compositional Distributional Model of Meaning

Cited by in corpus (9)

• The Frobenius anatomy of word meanings I: subject and object relative pronouns
• Lambek vs. Lambek: Functorial Vector Space Semantics and String Diagrams for Lambek Calculus
• Domain and Function: A Dual-Space Model of Semantic Relations and Compositions
• A Study of Entanglement in a Categorical Framework of Natural Language
• The Frobenius anatomy of word meanings II: possessive relative pronouns
• Category-Theoretic Quantitative Compositional Distributional Models of Natural Language Semantics
• Evaluating Neural Word Representations in Tensor-Based Compositional Settings
• Semantic Composition and Decomposition: From Recognition to Generation
• Using Sentence Plausibility to Learn the Semantics of Transitive Verbs